Unified framework for precise vision-aided navigation

Abstract

A system and method for efficiently locating in 3D an object of interest in a target scene using video information captured by a plurality of cameras. The system and method provide for multi-camera visual odometry wherein pose estimates are generated for each camera by all of the cameras in the multi-camera configuration. Furthermore, the system and method can locate and identify salient landmarks in the target scene using any of the cameras in the multi-camera configuration and compare the identified landmark against a database of previously identified landmarks. In addition, the system and method provide for the integration of video-based pose estimations with position measurement data captured by one or more secondary measurement sensors, such as, for example, Inertial Measurement Units (IMUs) and Global Positioning System (GPS) units.

Description

CROSS-REFERENCE TO RELATED APPLICATION[0001]This application claims the benefit of U.S. Provisional Application No. 60 / 868,227, filed on Dec. 1, 2006. U.S. Provisional Application No. 60 / 868,227 is incorporated by reference herein.STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT[0002]The U.S. Government has a paid-up license in this invention and the right in limited circumstances to require the patent owner to license others on reasonable terms as provided for by the terms of Contract No. M67854-05-C-8006 awarded by the Office of Naval Research.FIELD OF THE INVENTION[0003]The present invention relates generally to visual odometry, particularly to a system and method for enhanced route visualization in mission planning applications.BACKGROUND OF THE INVENTION[0004]Precise and efficient navigation systems are very important for many applications involving location identification, route planning, autonomous robot navigation, unknown environment map building, etc. Howeve...

AI Technical Summary

Benefits of technology

The present invention provides a system and method for real-time capture of visual sensor data and the ability to accurately locate an object in a GPS-denied or GPS-challenged environment. The system uses video cameras and other sensors to track features in the environment and estimate the position and orientation of the sensor system in 3D. The system can also integrate information from secondary sensors like IMUs and GPS units to improve localization accuracy. The invention also includes a landmark recognition system that can identify salient landmarks in the environment and match them against a database of previously identified landmarks. The system can record detailed information and imagery about the environment and assist in planning and implementing future navigation tasks.

Problems solved by technology

However, most of the available navigation systems do not function efficiently and fail frequently under certain circumstances.

However, GPS is limited in that it cannot work reliably once the satellite signals are blocked or unavailable in, for example, “GPS-denied” environments such as indoors, forests, urban areas, etc.

Even when operating properly, GPS can only provide the location of the user, which is not sufficient to assist the user during navigation.

In addition, conventional systems including multiple cameras or other visual sensing devices provide for limited ability to perform comprehensive visual odometry.

Images